Review Exercise on Analytics

1. Define AI and specify the role of AI.

Artificial intelligence (AI) is wide-ranging branch of computer science

concerned with building smart machines capable of performing tasks
that typically require human intelligence. AI is an interdisciplinary science with
multiple approaches, but advancements in machine learning and deep
learning are creating a paradigm shift in virtually every sector of the tech
industry. 
We are growing at huge rate, say it in terms of population, scripted knowledge,
tasks etc. Increasing in scale also increase entropy in system, demanding huge
number of tasks to be automated, and centralized. AI in simple words is
implementing human senses in machines. Humans will surely benefit from UI.
Though we are seeing automation of tasks is leading to job cutting, in long term
it is going to turn out to be a major benefit.

AI can surely process all trivial tasks at huge pace compared to humans.

Traffic Control, Automating Support, Automating Manufacturing, Fraud

Detection, Imposing Laws without corruption etc. It has many good uses.

2. What are the key differences between Machine Learning (ML) and
Deep Learning?

Machine Learning  Deep Learning 

The intention of ML is to enable
machines to learn by themselves using
the provided data and make accurate
predictions.
ML is a subset of artificial intelligence;
in fact, it’s simply a technique for
realizing AI.It is a method of training
algorithms such that they can learn how
to make decisions.
Deep learning is a subset of ML; in
fact, it’s simply a technique for
realizing machine learning. In other
words, DL is the next evolution of
machine learning.
DL algorithms are roughly inspired
by the information processing
patterns found in the human brain.
Training in machine learning entails
giving a lot of data to the algorithm and
allowing it to learn more about the
processed information.
Furthermore, in contrast to ML, DL
needs high-end machines and
considerably big amounts of training
data to deliver accurate results.
Just like we use our brains to identify
patterns and classify various types of
information, deep learning
algorithms can be taught to
accomplish the same tasks for
machines.
For example, while DL can
automatically discover the features to
be used for classification, ML
requires these features to be provided
manually.

3. What are the different types of learning that algorithms use?

There some variations of how to define the types of Machine Learning
Algorithms but commonly they can be divided into categories according to their
purpose and the main categories are the following:

 Supervised learning
Supervised Learning Algorithms are the ones that involve direct supervision
(cue the title) of the operation. In this case, the developer labels sample data
corpus and set strict boundaries upon which the algorithm operates. The
primary purpose of supervised learning is to scale the scope of data and to
make predictions of unavailable, future or unseen data based on labeled sample
data.
 Unsupervised Learning
Unsupervised Learning is the one that does not involve direct control of the
developer. If the main point of supervised machine learning is that you know
the results and need to sort out the data, then in case of unsupervised machine
learning algorithms the desired results are unknown and yet to be defined.
 Semi-supervised Learning
Semi-supervised learning algorithms represent a middle ground between
supervised and unsupervised algorithms. In essence, the semi-supervised model
combines some aspects of both into a thing of its own.
 Reinforcement Learning
Reinforcement learning represents what is commonly understood as machine
learning artificial intelligence.
In essence, reinforcement learning is all about developing a self-sustained
system that, throughout contiguous sequences of tries and fails, improves itself
based on the combination labeled data and interactions with the incoming data.
 4. What algorithms would you use for natural language processing?
How would these be of help in your apps?

NLP is a field in machine learning with the ability of a computer to understand,

analyze, manipulate, and potentially generate human language. Natural language
processing algorithms support computers by simulating the human ability to
understand language.
NLP is used to analyze text, allowing machines to understand how human’s
speak. This human-computer interaction enables real-world applications
like automatic text summarization, sentiment analysis, topic extraction, named
entity recognition, parts-of-speech tagging, relationship extraction, stemming,
and more. NLP is commonly used for text mining, machine translation,
and automated question answering.

One particular algorithm is the part-of-speech (POS) tagger. A POS tagger is

used to automatically assign parts of speech to every word in a piece of text.
This POS tagger classifies words in text based on lexical features and analyzes
them in relation to other words around them.

Boilerpipe is an extremely robust and efficient algorithm for removing “clutter”

that identifies the main content of a news article by analyzing different content
blocks using features like length of an average sentence, types of tags used in
content blocks, and density of links. The boilerpipe algorithm has proven to be
competitive with other much more computationally expensive algorithms, such
as those based on machine vision.

5. What is the advantage of using Convolutional Neural Networks

(CNN) in a production shop e.g. in a Maruti plant? How would these
be of assistance in apps that you create?
For what kind of apps are RNN algorithms used?
A Convolutional Neural Network (ConvNet/CNN) is a Deep Learning
algorithm which can take in an input image, assign importance (learnable
weights and biases) to various aspects/objects in the image and be able to
differentiate one from the other. The pre-processing required in a ConvNet is
much lower as compared to other classification algorithms.
The main advantage of CNN compared to its predecessors is that it automatically
detects the important features without any human supervision.
Convolutional Neural Networks (CNN) can be used in a production shop
e.g. in a Maruti plant to automate material quality inspection
  Deep learning techniques, and in particular Convolutional Neural
Networks (CNNs), have led to significant progress in image processing. 
 These applications could serve as a basis for the development of expertise
assistance or automatic screening tools. Today’s increased level of
automation in manufacturing also demands automation of material quality
inspection with little human intervention. To stay competitive, modern
Industrial firms strive to achieve both quantity and quality with
automation without compromising one over the other.
 To meet industry standards quality inspectors in manufacturing firms
inspect product quality usually after the product is manufactured, it’s a
time consuming manual effort and a rejected product results in wasted
upstream factory capacity, consumables, labor and cost.
 With the modern trend of Artificial Intelligence, industrial firms are
looking to use deep learning-based computer vision technology during the
production cycle itself to automate material quality inspection.
 The goal is to minimize human intervention at the same time reach human
level accuracy or more as well as optimize factory capacity, labor cost etc.
 During our hardware manufacturing processes there could be damages
such scratches / cracks which make our products unusable for the next
processes in the production line.
 Deep learning application such as CNN can detect defect such as a crack /
scratch in milliseconds with human level accuracy and better as well as
interpreted the defect area in the image with heat maps.
CNN is also computationally efficient. It uses special convolution and pooling
operations and performs parameter sharing. This enables CNN models to run on
any device, making them universally attractive.
A recurrent neural network (RNN) is a class of artificial neural
networks where connections between nodes form a directed graph along a
temporal sequence. This allows it to exhibit temporal dynamic behavior.
Unlike feedforward neural networks, RNNs can use their internal state
(memory) to process sequences of inputs. This makes them applicable to tasks
such as unsegmented, connected handwriting recognition[1] or speech
recognition.